Object and Relation Centric Representations for Push Effect Prediction
Object and Relation Centric Representations for Push Effect Prediction
复制标题
DOI：
10.1016/j.robot.2024.104632
复制
发表时间：
2021-02
期刊：
影响因子：
--
通讯作者：
Ahmet E. Tekden;Aykut Erdem;Erkut Erdem;T. Asfour;Emre Ugur
中科院分区：
文献类型：
--
作者：
Ahmet E. Tekden;Aykut Erdem;Erkut Erdem;T. Asfour;Emre Ugur
推是一种基本的非抓取操作技能，用于从预抓取操作到场景重排，推理场景中的对象关系等任务，因此推动作在机器人中得到了广泛的研究。有效地使用推动动作通常需要理解被操纵对象的动力学，并适应预测与现实之间的差异。由于这个原因，在文献中已经大量研究了具有推动动作的效果预测和参数估计。然而，目前的方法是有限的，因为它们要么模型系统具有固定数量的对象或使用基于图像的表示，其输出不是很可解释，并迅速积累错误。在本文中，我们提出了一个基于图神经网络的框架，通过建模对象关系的接触或关节的推动行动的效果预测和参数估计。我们的框架在真实的和模拟环境中进行了验证，这些环境包含通过不同类型的关节连接的不同形状的多部分对象和具有不同质量的对象，并且它在物理预测方面优于基于图像的表示。我们的方法使机器人能够预测和适应推动作的效果，因为它观察到的场景。它也可以用于从未见过的工具的工具操作。此外，我们证明了6D效果预测的上下文中的机器人为基础的硬盘拆卸的动作。
Pushing is an essential non-prehensile manipulation skill used for tasks ranging from pre-grasp manipulation to scene rearrangement, reasoning about object relations in the scene, and thus pushing actions have been widely studied in robotics. The effective use of pushing actions often requires an understanding of the dynamics of the manipulated objects and adaptation to the discrepancies between prediction and reality. For this reason, effect prediction and parameter estimation with pushing actions have been heavily investigated in the literature. However, current approaches are limited because they either model systems with a fixed number of objects or use image-based representations whose outputs are not very interpretable and quickly accumulate errors. In this paper, we propose a graph neural network based framework for effect prediction and parameter estimation of pushing actions by modeling object relations based on contacts or articulations. Our framework is validated both in real and simulated environments containing different shaped multi-part objects connected via different types of joints and objects with different masses, and it outperforms image-based representations on physics prediction. Our approach enables the robot to predict and adapt the effect of a pushing action as it observes the scene. It can also be used for tool manipulation with never-seen tools. Further, we demonstrate 6D effect prediction in the lever-up action in the context of robot-based hard-disk disassembly.